{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MXIIC4ERTXJMEB6SDBQAX6FEBS","short_pith_number":"pith:MXIIC4ER","schema_version":"1.0","canonical_sha256":"65d08170919dd2c207d218600bf8a40ca3a8b1af601c83d4f551bcb3d3e4be5f","source":{"kind":"arxiv","id":"2311.02392","version":1},"attestation_state":"computed","paper":{"title":"Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Asako Kanezaki, Hao Zheng, Jianzhuang Liu, Runqi Wang","submitted_at":"2023-11-04T12:28:04Z","abstract_excerpt":"The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset. However, in practice, the base and the target datasets of few-shot classification are usually from different domains, which is the problem of cross-domain few-shot classification. We tackle this problem by making a small proportion of unlabeled images in the target domain accessible in the training stage. In this setup, even though the base data are sufficient and labeled, the large domain shift still "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.02392","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-04T12:28:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6257cda2d3e69a6c3c96a7bfb855e2beeec03dad5a426d4be54b041d64ff796e","abstract_canon_sha256":"8b6348e88dc78cb9ce1194fde7dad65ef290bb89cc5fc35703ff62d12b42166d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:11.351619Z","signature_b64":"JAQRrpt1A1kfNNyh2BRWWV20tYZJSn8eculr6J4yywLDYNZdHw8fYiJ8LInwIdC4t3P1nJNbt6/UOcrIGOcxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d08170919dd2c207d218600bf8a40ca3a8b1af601c83d4f551bcb3d3e4be5f","last_reissued_at":"2026-07-05T07:09:11.351039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:11.351039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Asako Kanezaki, Hao Zheng, Jianzhuang Liu, Runqi Wang","submitted_at":"2023-11-04T12:28:04Z","abstract_excerpt":"The conventional few-shot classification aims at learning a model on a large labeled base dataset and rapidly adapting to a target dataset that is from the same distribution as the base dataset. However, in practice, the base and the target datasets of few-shot classification are usually from different domains, which is the problem of cross-domain few-shot classification. We tackle this problem by making a small proportion of unlabeled images in the target domain accessible in the training stage. In this setup, even though the base data are sufficient and labeled, the large domain shift still "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02392","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.02392/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.02392","created_at":"2026-07-05T07:09:11.351106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02392v1","created_at":"2026-07-05T07:09:11.351106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02392","created_at":"2026-07-05T07:09:11.351106+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXIIC4ERTXJM","created_at":"2026-07-05T07:09:11.351106+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXIIC4ERTXJMEB6S","created_at":"2026-07-05T07:09:11.351106+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXIIC4ER","created_at":"2026-07-05T07:09:11.351106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00767","citing_title":"Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS","json":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS.json","graph_json":"https://pith.science/api/pith-number/MXIIC4ERTXJMEB6SDBQAX6FEBS/graph.json","events_json":"https://pith.science/api/pith-number/MXIIC4ERTXJMEB6SDBQAX6FEBS/events.json","paper":"https://pith.science/paper/MXIIC4ER"},"agent_actions":{"view_html":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS","download_json":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS.json","view_paper":"https://pith.science/paper/MXIIC4ER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02392&json=true","fetch_graph":"https://pith.science/api/pith-number/MXIIC4ERTXJMEB6SDBQAX6FEBS/graph.json","fetch_events":"https://pith.science/api/pith-number/MXIIC4ERTXJMEB6SDBQAX6FEBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS/action/storage_attestation","attest_author":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS/action/author_attestation","sign_citation":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS/action/citation_signature","submit_replication":"https://pith.science/pith/MXIIC4ERTXJMEB6SDBQAX6FEBS/action/replication_record"}},"created_at":"2026-07-05T07:09:11.351106+00:00","updated_at":"2026-07-05T07:09:11.351106+00:00"}